Neural Machine Translation (NMT) has drawn much attention
due to its promising translation performance in recent
years. However, the under-translation problem still remains a
big challenge. In this paper, we focus on the under-translation
problem and attempt to find out what kinds of words are
more likely to be ignored. Through analysis, we observe that
a source word with a larger translation entropy is more inclined
to be dropped. To address this problem, we proposed
a coarse-to-fine framework, in which we first introduce a
simple strategy to reduce the entropy of high-entropy words
through constructing the pseudo target sentences. Then we
propose three methods, including pre-training method, multitask
method and two-pass method, to encourage the neural
model to focus on these high-entropy words. Experimental
results on various translation tasks show that our method can
significantly improve the translation quality and substantially
reduce the under-translation cases of high-entropy words.